Instructions to use rbelanec/train_codealpacapy_42_1767887026 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_codealpacapy_42_1767887026 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbelanec/train_codealpacapy_42_1767887026")

Transformers

How to use rbelanec/train_codealpacapy_42_1767887026 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rbelanec/train_codealpacapy_42_1767887026")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_codealpacapy_42_1767887026", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rbelanec/train_codealpacapy_42_1767887026 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_codealpacapy_42_1767887026"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_codealpacapy_42_1767887026",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_codealpacapy_42_1767887026

SGLang

How to use rbelanec/train_codealpacapy_42_1767887026 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rbelanec/train_codealpacapy_42_1767887026" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_codealpacapy_42_1767887026",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rbelanec/train_codealpacapy_42_1767887026" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_codealpacapy_42_1767887026",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_codealpacapy_42_1767887026 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_codealpacapy_42_1767887026
```

train_codealpacapy_42_1767887026

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the codealpacapy dataset. It achieves the following results on the evaluation set:

Loss: 0.4641
Num Input Tokens Seen: 10214104

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.31	0.5001	1908	0.5422	509696
0.4525	1.0003	3816	0.4955	1019912
0.3652	1.5004	5724	0.4801	1533144
0.3695	2.0005	7632	0.4760	2042048
0.3682	2.5007	9540	0.4739	2547808
0.4507	3.0008	11448	0.4706	3062008
0.5541	3.5009	13356	0.4688	3566184
0.5049	4.0010	15264	0.4691	4082080
0.5938	4.5012	17172	0.4669	4595520
0.4097	5.0013	19080	0.4665	5105064
0.3633	5.5014	20988	0.4645	5623240
0.5529	6.0016	22896	0.4681	6127632
0.4049	6.5017	24804	0.4646	6636608
0.5062	7.0018	26712	0.4646	7148208
0.5667	7.5020	28620	0.4641	7662240
0.3807	8.0021	30528	0.4648	8170632
0.4253	8.5022	32436	0.4644	8676728
0.4878	9.0024	34344	0.4644	9194752
0.6231	9.5025	36252	0.4644	9710784

Framework versions

PEFT 0.17.1
Transformers 4.51.3
Pytorch 2.9.1+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for rbelanec/train_codealpacapy_42_1767887026

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Adapter

(2408)

this model